Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UTF
    -0.06
    가
    -0.06
     vào
    -0.06
    ién
    -0.06
     chased
    -0.06
     Qualified
    -0.06
    cap
    -0.06
    將
    -0.06
     bajo
    -0.06
    enever
    -0.05
    POSITIVE LOGITS
    \Validation
    0.07
     побед
    0.07
     tostring
    0.07
    \":{\"
    0.06
     Smash
    0.06
     декоратив
    0.06
    (viewModel
    0.06
     pItem
    0.06
     GetType
    0.06
    .magnitude
    0.06
    Act Density 0.067%

    No Known Activations